Augmented Fairness: An Interpretable Model Augmenting Decision-Makers' Fairness
This addresses fairness enhancement for real-world decision systems where only black-box access is available, though it represents an incremental improvement combining existing fairness and interpretability techniques.
The paper tackles the problem of mitigating prediction bias in black-box decision-makers (including human decision-makers) by detecting biased regions in feature space and replacing them with interpretable decision rules that balance predictive performance and fairness. The approach achieved competitive results on public datasets while operating under budget constraints for label queries.
We propose a model-agnostic approach for mitigating the prediction bias of a black-box decision-maker, and in particular, a human decision-maker. Our method detects in the feature space where the black-box decision-maker is biased and replaces it with a few short decision rules, acting as a "fair surrogate". The rule-based surrogate model is trained under two objectives, predictive performance and fairness. Our model focuses on a setting that is common in practice but distinct from other literature on fairness. We only have black-box access to the model, and only a limited set of true labels can be queried under a budget constraint. We formulate a multi-objective optimization for building a surrogate model, where we simultaneously optimize for both predictive performance and bias. To train the model, we propose a novel training algorithm that combines a nondominated sorting genetic algorithm with active learning. We test our model on public datasets where we simulate various biased "black-box" classifiers (decision-makers) and apply our approach for interpretable augmented fairness.